Ship Detection in SAR Imagery via Variational Bayesian Inference

Song, Shaoxu; Xu, Bin; Li, Zeng-hui; Yang, Jian

doi:10.1109/lgrs.2015.2510378

Cited by 28 publications

(10 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A method based on variational Bayesian inference for multitarget situation and very complex backgrounds is proposed in Ref. 15. Some more sophisticated methods rely on multichannel information, such as polarimetric detectors 16 or along-track interferometry.…”

Section: Vessel Detection From Spacementioning

confidence: 99%

Object-based image analysis approach for vessel detection on optical and radar images

Aiello

Vezzoli

Gianinetto

2019

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

Commercial satellites for Earth observation can integrate conventional positioning and tracking systems for monitoring legal and illegal activities by sea, in order to effectively detect and prevent events threatening human life and environment. This study describes an object-oriented approach to detect vessels combining high-and medium-resolution optical and radar images. Once detected, the algorithm estimates their position, length, and heading and assigns a speed range. Tests are done using WorldView-2, QuickBird, GeoEye-1, Sentinel-2A, COSMO-SkyMed, and Sentinel-1 data imaged in several test sites including China, Australia, Italy, Hong Kong, and the western Mediterranean Sea. Validation of results with data from the automatic identification system shows that the estimates for length and heading have R 2 ¼ 0.85 and R 2 ¼ 0.92, respectively. Tests for evaluating speed from Sentinel-2 time-lag image displacement show encouraging results, with 70% of estimates' residuals within AE2 m∕s. Finally, our method is compared to the state-of-the-art search for unidentified maritime object (SUMO), provided by the European Commission's Joint Research Centre. Finally, our method is compared to the state-of-the-art SUMO. Tests with Sentinel-1 data show similar results in terms of correct detections. Nevertheless, our method returns a smaller number of false alarms compared to SUMO.

show abstract

Section: Vessel Detection From Spacementioning

confidence: 99%

Object-based image analysis approach for vessel detection on optical and radar images

Aiello

Vezzoli

Gianinetto

2019

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

show abstract

“…Both classes of algorithms are widely applied in automated driving, intelligent security, remote sensing detection and other fields. For SAR image object detection tasks, compared with traditional constant false alarm rate (CFAR) algorithms [14], [15], ship detection algorithms based on deep learning do not require complex modeling processes; consequently, they have attracted considerable research interest from scholars. Li et al applied the various training strategies to improve the Faster R-CNN detection algorithm for ship detection in SAR images [16].…”

Section: Introductionmentioning

confidence: 99%

A Deep Neural Network Based on an Attention Mechanism for SAR Ship Detection in Multiscale and Complex Scenarios

Chen

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Synthetic aperture radar (SAR) ship detection based on deep learning has been widely applied in recent years. However, two main obstacles are hindering SAR ship detection. First, the identification of ships in a port is seriously disrupted by the presence of onshore buildings. It is difficult for the existing detection algorithms to effectively distinguish the targets from such a complex background. Additionally, it appears more complicated to accurately locate densely arranged ships. Second, the ships in SAR images exist at a variety of scales due to multiresolution imaging modes and the variety of ship shapes; these pose a much greater challenge to ship detection. To solve the above problems, this paper proposes an object detection network combined with an attention mechanism to accurately locate targets in complex scenarios. To address the diverse scales of ship targets, we construct a loss function that incorporates the generalized intersection over union (GIoU) loss to reduce the scale sensitivity of the network. For the final processing of the results, soft nonmaximum suppression (Soft-NMS) is also introduced into the model to reduce the number of missed detections for ship targets in the presence of severe overlap. The experimental results reveal that the proposed model exhibits excellent performance on the extended SAR ship detection dataset (SSDD) while achieving real-time detection. INDEX TERMS Ship detection, synthetic aperture radar (SAR), deep neural network, attention mechanism.

show abstract

“…Therefore, ship detection from PolSAR images has drawn increasing attention in recent years. Featured by adaptive detection threshold, CFAR has become one of the most popular ship detectors [1][2][3][4][5][6]. However, its performance strongly depends on statistical modeling of the local background clutter and empirical sliding window size (i.e., the target window, protect window, and background window).…”

Section: Introductionmentioning

confidence: 99%

Ship Detection Using Deep Convolutional Neural Networks for PolSAR Images

et al. 2019

View full text Add to dashboard Cite

Ship detection plays an important role in many remote sensing applications. However, the performance of the PolSAR ship detection may be degraded by the complicated scattering mechanism, multi-scale size of targets, and random speckle noise, etc. In this paper, we propose a ship detection method for PolSAR images based on modified faster region-based convolutional neural network (Faster R-CNN). The main improvements include proposal generation by adopting multi-level features produced by the convolution layers, which fits ships with different sizes, and the addition of a Deep Convolutional Neural Network (DCNN)-based classifier for training sample generation and coast mitigation. The proposed method has been validated by four measured datasets of NASA/JPL airborne synthetic aperture radar (AIRSAR) and uninhabited aerial vehicle synthetic aperture radar (UAVSAR). Performance comparison with the modified constant false alarm rate (CFAR) detector and the Faster R-CNN has demonstrated that the proposed method can improve the detection probability while reducing the false alarm rate and missed detections.

show abstract

Ship Detection in SAR Imagery via Variational Bayesian Inference

Cited by 28 publications

References 10 publications

Object-based image analysis approach for vessel detection on optical and radar images

Object-based image analysis approach for vessel detection on optical and radar images

A Deep Neural Network Based on an Attention Mechanism for SAR Ship Detection in Multiscale and Complex Scenarios

Ship Detection Using Deep Convolutional Neural Networks for PolSAR Images

Contact Info

Product

Resources

About